• 전기학회논문지
• /
• 제59권2호
• /
• pp.429-435
• /
• 2010

Three dimensional (3-D) object detection and pose estimation from a single view query image has been an important issue in various fields such as medical applications, robot vision, and manufacturing automation. However, most of the existing methods are not appropriate in a real time environment since object detection and pose estimation requires extensive information and computation. In this paper, we present a fast 3-D object detection and pose estimation scheme based on surrounding camera view-changed images of objects. Our scheme has two parts. First, we detect images similar to the query image from the database based on the shape feature, and calculate candidate poses. Second, we perform accurate pose estimation for the candidate poses using the scale invariant feature transform (SIFT) method. We earned out extensive experiments on our prototype system and achieved excellent performance, and we report some of the results.

• 전자공학회논문지B
• /
• 제30B권7호
• /
• pp.59-69
• /
• 1993

In this paper, a new matching strategy for 3-D object recognition, based on the Surface Normal Images (SNIs), is proposed. The matching strategy using the similarity decision function [9,10] lost the efficiency and the reliability of matching, because all features of models within model base must be compared with the scene object features, and the weights of the attributes of features is given by heuristic manner. However, the proposed matching strategy can solve these problems by using a new approach. In the approach, by searching the model base, a model object whose features are fully matched with the features of sceme object is selected. In this paper, the model base is constructed for the total 26 objects, and systhetic and real range images are used in the test of the system operation. Experimental result is performed to show the possibility that this strategy can be effectively used for the SNI based recognition.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 1998년도 국제 컨퍼런스: 국가경쟁력 향상을 위한 디지틀도서관 구축방안
• /
• pp.406-420
• /
• 1998

Users want to browse various stoups of nested attribute values of an object. On the other hand, in case of the presentation of a multimedia object, the form-based presentation is superior to the graph-based presentation. Therefore we propose o form-based presentation transformation scheme that allows users to reorganize the presentation layout to ft the limited screen and to show the values of all the needed attributes. For the representation of the presentation scenario of an object a presentation information class and the presentation transformation operations are defined. We show how these operations transform the default presentation into the wanted presentation by navigating through a multimedia object with the COMIB (COMposite Icon Browser).

• 한국정보처리학회논문지
• /
• 제6권10호
• /
• pp.2680-2692
• /
• 1999

Software quality is classified by quality of process and product. In experience of Quality Management, it is known that quality level of product as it depends on goodness and badness of process and organization. As a result, improvement of software process has been important subject. According as this trends, ISO 12207 is publicated as standard of software life cycle process by ISO. For UML based object oriented development process, it is necessary that we should research detailed definition of activity and task of ISO 12207 process which is added, deleted or tailored in according to organization and project characteristics. In this thesis, by according with ISO 12207 software life cycle process, UML based object oriented development process is proposed. This process is composed of 7 steps and 19 activities including development phase, activity and product to improve quality of reliability. Usefulness of object oriented process for improvement of software quality is proved at three ways, which are comparative analysis of process characteristics, SPICE process evaluation and SPICE rick analysis.

• 한국멀티미디어학회논문지
• /
• 제24권3호
• /
• pp.345-354
• /
• 2021

Recently, deep learning-based image recognition systems have been adopted to various surveillance environments, but most of them are still picture-type object recognition methods, which are insufficient for the long term temporal analysis and high-dimensional situation management. Therefore, we propose a method recognizing the specific dangerous situation generated by human in real-time, and utilizing deep learning-based object analysis techniques. The proposed method uses deep learning-based object detection and tracking algorithms in order to recognize the situations such as 'trespassing', 'loitering', and so on. In addition, human's joint pose data are extracted and analyzed for the emergent awareness function such as 'falling down' to notify not only in the security but also in the emergency environmental utilizations.

• Current Optics and Photonics
• /
• 제6권5호
• /
• pp.463-472
• /
• 2022

At certain wavelengths, single-pixel imaging is considered to be a solution that can achieve high quality imaging and also reduce costs. However, achieving imaging of complex scenes is an overhead-intensive process for single-pixel imaging systems, so low efficiency and high consumption are the biggest obstacles to their practical application. Improving efficiency to reduce overhead is the solution to this problem. Salient object detection is usually used as a pre-processing step in computer vision tasks, mimicking human functions in complex natural scenes, to reduce overhead and improve efficiency by focusing on regions with a large amount of information. Therefore, in this paper, we explore the implementation of salient object detection based on single-pixel imaging after a single pixel, and propose a scheme to reconstruct images based on Fourier bases and use U²Net models for salient object detection.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.65-71
• /
• 2024

An indirect visual SLAM takes raw image data and exploits geometric information such as key-points and line edges. Due to various environmental changes, SLAM performance may decrease. The main problem is caused by dynamic objects especially in highly crowded environments. In this paper, we propose a robust feature-based visual SLAM, building on ORB-SLAM, via multi-channel dynamic objects estimation. An optical flow and deep learning-based object detection algorithm each estimate different types of dynamic object information. Proposed method incorporates two dynamic object information and creates multi-channel dynamic masks. In this method, information on actually moving dynamic objects and potential dynamic objects can be obtained. Finally, dynamic objects included in the masks are removed in feature extraction part. As a results, proposed method can obtain more precise camera poses. The superiority of our ORB-SLAM was verified to compared with conventional ORB-SLAM by the experiment using KITTI odometry dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2067-2081
• /
• 2024

Recently, image analysis research has been actively conducted due to the accumulation of big image data and the development of deep learning. Image analytics research has different characteristics from other data such as data size, real-time, image quality diversity, structural complexity, and security issues. In addition, a large amount of data is required to effectively analyze images with deep-learning models. However, in many fields, the data that can be collected is limited, so there is a need for meta learning based image analysis technology that can effectively train models with a small amount of data. This paper presents a comprehensive survey of meta-learning-based object-tracking techniques. This approach comprehensively explores object tracking methods and research that can achieve high performance in data-limited situations, including key challenges and future directions. It provides useful information for researchers in the field and can provide insights into future research directions.

• 한국지리정보학회지
• /
• 제20권1호
• /
• pp.1-14
• /
• 2017

토지피복도는 지역의 현황을 파악하는 기초적 자료이지만 시간적 공간적 해상도의 한계로 인하여 생태 연구 분야에서의 활용성은 떨어지는 측면이 있다. 이에 본 연구에서는 UAV으로 취득된 고해상도 영상을 기반으로 토지피복도 제작과 자료의 활용가능성을 알아보고자 하였다. UAV를 이용하여 연구대상지 $2.5km^2$ 범위에서 10.5cm 정사영상을 취득하였으며 객체기반(Object-based)과 화소기반(pixel-based) 분류를 통해 얻어진 토지피복도를 비교 분석하였다. 정확도 검증 결과 화소기반 분류는 Kappa 0.77, 객체기반 분류는 Kappa 0.82로 분류정확도가 높았으며, 전반적인 면적비율은 유사하지만 초지, 습지 지역에서 양호한 분류 결과가 나타났다. 객체기반 분류를 위한 최적의 영상분할 가중치는 Scale150, Shape 0.5, Compactness 0.5, Color 1로 선정하였으며 가중치 선정과정에서 Scale이 가장 큰 영향을 주었다. 화소기반 분류 결과와 비교해 객체간의 명확한 경계를 가지므로 결과물 판독이 용이한 것으로 나타났으며, 환경부 토지피복도(세분류)와 비교하여 개발지역(도로, 건물 등)을 제외한 자연지역(산림, 초지, 습지 등)의 분류에 효과적이었다. UAV 영상을 활용한 토지피복 분류방법으로서 객체기반 분류기법의 적용은 자료의 최신성, 정확성, 경제성 등의 장점으로 생태 연구 분야에 기여할 수 있을 것으로 판단된다.

• 지능정보연구
• /
• 제28권1호
• /
• pp.89-106
• /
• 2022

최근 영상 데이터의 급증으로 이를 효과적으로 처리하기 위해 객체 탐지 및 추적, 행동 인식, 표정 인식, 재식별(Re-ID)과 같은 다양한 컴퓨터비전 기술에 대한 수요도 급증했다. 그러나 객체 탐지 및 추적 기술은 객체의 영상 촬영 장소 이탈과 재등장, 오클루전(Occlusion) 등과 같이 성능을 저하시키는 많은 어려움을 안고 있다. 이에 따라 객체 탐지 및 추적 모델을 근간으로 하는 행동 및 표정 인식 모델 또한 객체별 데이터 추출에 난항을 겪는다. 또한 다양한 모델을 활용한 딥러닝 아키텍처는 병목과 최적화 부족으로 성능 저하를 겪는다. 본 연구에서는 YOLOv5기반 DeepSORT 객체추적 모델, SlowFast 기반 행동 인식 모델, Torchreid 기반 재식별 모델, 그리고 AWS Rekognition의 표정 인식 모델을 활용한 영상 분석 시스템에 단일 연결 계층적 군집화(Single-linkage Hierarchical Clustering)를 활용한 재식별(Re-ID) 기법과 GPU의 메모리 스루풋(Throughput)을 극대화하는 처리 기법을 적용한 행동 및 표정 검출용 영상 분석 시스템을 제안한다. 본 연구에서 제안한 시스템은 간단한 메트릭을 사용하는 재식별 모델의 성능보다 높은 정확도와 실시간에 가까운 처리 성능을 가지며, 객체의 영상 촬영 장소 이탈과 재등장, 오클루전 등에 의한 추적 실패를 방지하고 영상 내 객체별 행동 및 표정 인식 결과를 동일 객체에 지속적으로 연동하여 영상을 효율적으로 분석할 수 있다.